Novita AI API

LLM 6.0/10

DeepSeek V3.1 $0.27/M (cache read $0.135), DeepSeek V3 0324 $0.27/M, broad open catalog (Qwen/Llama/DeepSeek). GPU + serverless

Novita AI API scores 6/10 for free value in LLM. The main constraint: Paid — Pay-as-you-go, from $0.27/M. DeepSeek V3.1 $0.27/M (cache read $0.135), DeepSeek V3 0324 $0.27/M, broad open catalog (Qwen/Llama/DeepSeek). GPU + serverless.

Category LLM Kind Paid plan

Free value score

6.0 / 10

Show the math

Model Quality 3.8/10

value = 21 artificial_analysis_score

weighted score = 0.2 * 3.8/10

Access 10/10

value = 10/10

weighted score = 0.1 * 10/10

Price Efficiency 6.1/10

value = 3703704 tok/$

weighted score = 0.7 * 6.1/10

Key metrics

DeepSeek V3.1 21 Best model

$0.27/M Price

What you get

Paid — Pay-as-you-go, from $0.27/M. DeepSeek V3.1 $0.27/M (cache read $0.135), DeepSeek V3 0324 $0.27/M, broad open catalog (Qwen/Llama/DeepSeek). GPU + serverless

~3.7M tokens/$1 on DeepSeek V3.1; cache read doubles it to ~7.4M/$1

Gotchas

No gotchas documented yet. Contribute one if you know a constraint we missed.

Sources

"DeepSeek V3.1, 131,072, $0.27 /Mt·Cache Read $0.135 /Mt ; DeepSeek V3 0324, 163,840, $0.27 /Mt"
https://novita.ai/pricing
"In reasoning mode, DeepSeek V3.2 scores 66 on the Artificial Analysis Intelligence Index"
https://www.linkedin.com/pulse/deepseek-v32-2-most-intelligent-open-weights-model-qnwoc

paid value llm-providers

Open service ← All LLM

Alternatives

Same category · similar quota

Moonshot Kimi APIMoonshot Kimi API · paid · Paid plan

6.0

Kimi K2/K2.5: $0.15/M input (Nov-2025 pricing, 75% off) to $0.60/M, $2.50-3.00/M output, 256K context; K2.5 adds multimodal

3.8M/$19.4 AA3.8M/$

May be outdatedChecked 26d ago

Paid onlyEmbeddingsMetered

DeepSeek Platform APIDeepSeek Platform API · paid · Paid plan

6.2

deepseek-chat (V3.2): $0.028 cache / $0.28 input miss / $0.42 output per 1M; deepseek-reasoner (R1): $0.14/$0.55/$2.19, cheapest top-tier reasoning

4.1M/$24.7 AA4.1M/$

May be outdatedChecked 26d ago

Best valuePaid onlyMetered

ZenMux Builder ProZenMux Builder Pro · paid · Paid plan

6.2

150+ aggregated models (Claude, GPT-5.x, Gemini, GLM, Kimi) via one OpenAI/Anthropic-compatible key, billed in 'Flows': 50 Flows/5h, ~213/week, ~914/month max ≈ $30 of API value (1.5x multiplier)

1.5×40.2 AA1.5×

May be outdatedChecked 23d ago

NoncomPersonalPaid only